StyleRig: Rigging StyleGAN for 3D Control Over Portrait Images

StyleGAN generates photorealistic portrait images of faces with eyes, teeth, hair and context (neck, shoulders, background), but lacks a rig-like control over semantic face parameters that are interpretable in 3D, such as face pose, expressions, and scene illumination. Three-dimensional morphable fa...

Full description

Saved in:
Bibliographic Details
Main Authors: Tewari, Ayush, Elgharib, Mohamed, Bharaj, Gaurav, Bernard, Florian, Seidel, Hans-Peter, Perez, Patrick, Zollhofer, Michael, Theobalt, Christian
Format: Conference Proceeding
Language:English
Subjects:
Face
Gallium nitride
Image reconstruction
Lighting
Semantics
Three-dimensional displays
Training
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:StyleGAN generates photorealistic portrait images of faces with eyes, teeth, hair and context (neck, shoulders, background), but lacks a rig-like control over semantic face parameters that are interpretable in 3D, such as face pose, expressions, and scene illumination. Three-dimensional morphable face models (3DMMs) on the other hand offer control over the semantic parameters, but lack photorealism when rendered and only model the face interior, not other parts of a portrait image (hair, mouth interior, background). We present the first method to provide a face rig-like control over a pretrained and fixed StyleGAN via a 3DMM. A new rigging network, \textit{RigNet} is trained between the 3DMM's semantic parameters and StyleGAN's input. The network is trained in a self-supervised manner, without the need for manual annotations. At test time, our method generates portrait images with the photorealism of StyleGAN and provides explicit control over the 3D semantic parameters of the face.
ISSN:2575-7075
DOI:10.1109/CVPR42600.2020.00618